STRIKE beamlet parameters retreiving via Convolutional Neural Network

Journal of Heat Transfer, 2008

The use of artificial neural network (ANN), as one of the artificial intelligence methodologies, in a variety of real-world applications has been around for some time. However, the application of ANN to thermal science and engineering is still relatively new, but is receiving ever-increasing attention in recent published literature. Such attention is due essentially to special requirement and needs of the field of thermal science and engineering in terms of its increasing complexity and the recognition that it is not always feasible to deal with many critical problems in this field by the use of traditional analysis. The purpose of the present review is to point out the recent advances in ANN and its successes in dealing with a variety of important thermal problems. Some current ANN shortcomings, the development of recent advances in ANN-based hybrid analysis, and its future prospects will also be indicated.

The analysis of the internal defects (not detectable by a visual inspection) of the aircraft composite materials is a difficult task unless invasive techniques are applied. In this paper we have addressed the problem of inspecting composite materials by using automatic analysis of thermographic techniques. The proposed approach consists of two steps: at first a neural network was trained to model the time space variations in a sequence of thermgraphic images and then the same neural network was applied to all the points of a sequence of thermographic images. The experimental tests were performed on a composite material and they demonstrate the ability of the method to recognize regions containing defects even in presence of considerable lighting variations.

Applied Energy, 2024

• Deep Learning potential in the construction sector is explored. • Infrared imaging processing and interpretation is combined with the potential of AI. • Convolution Neural Networks are used for finding deficiencies in building envelopes. • Biomedical imaging techniques are applied to aerial infrared images of buildings.

2019

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of particles produced in high-energy physics collisions. We train neural networks on shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ...

2017

We present studies of the application of Deep Neural Networks and Convolutional Neural Networks for the classification, energy regression, and simulation of particles produced in high-energy particle collisions.We train cell-based Neural Nets that provide significant improvement in performance for particle classification and energy regression compared to feature-based Neural Nets and Boosted Decision Trees, and Generative Adversarial Networks that provide reasonable modeling of several but not all shower features.

Instruments

The Compact Muon Solenoid (CMS) is one of the general purpose detectors at the CERN Large Hadron Collider (LHC), where the products of proton–proton collisions at the center of mass energy up to 13.6 TeV are reconstructed. The electromagnetic calorimeter (ECAL) is one of the crucial components of the CMS since it reconstructs the energies and positions of electrons and photons. Even though several Machine Learning (ML) algorithms have been already used for calorimetry, with the constant advancement of the field, more and more sophisticated techniques have become available, which can be beneficial for object reconstruction with calorimeters. In this paper, we present two novel ML algorithms for object reconstruction with the ECAL that are based on graph neural networks (GNNs). The new approaches show significant improvements compared to the current algorithms used in CMS.

The Bulletin of the Polytechnic Institute of Jassy, Construction. Architecture Section, 2016

By applying the thermography and neural networks, a diagnosis of the heat loss can establish, followed by the state of a building. The infrared images recorded by the camera, obtained through the thermography, will be the input data for the artificial neural network. For this type of problem, a feed-forward, multilayer, supervised neural network is adopted and trained with a back-propagation algorithm. The activation function used in this matter is a function specific to the information classification problems, namely the step function.

Sensors

Advanced materials such as continuous carbon fiber-reinforced thermoplastic (CFRP) laminates are commonly used in many industries, mainly because of their strength, stiffness to weight ratio, toughness, weldability, and repairability. Structural components working in harsh environments such as satellites are permanently exposed to some sort of damage during their lifetimes. To detect and characterize these damages, non-destructive testing and evaluation techniques are essential tools, especially for composite materials. In this study, artificial intelligence was applied in combination with infrared thermography to detected and segment impact damage on curved laminates that were previously submitted to a severe thermal stress cycles and subsequent ballistic impacts. Segmentation was performed on both mid-wave and long-wave infrared sequences obtained simultaneously during pulsed thermography experiments by means of a deep neural network. A deep neural network was trained for each wav...

Neural Computing & Applications, 1997

Feedforward neural networks have been used for kinetic parameters determination and signal filtering in differential scanning calorimetry. The proper learning function was chosen and the network topology was optimised using an empiric procedure. The learning process was achieved using various simulated thermoanalytical curves computed for several thermodynamic and kinetic parameters. Various amounts of simulated noise were added on the power signals. The resilient-propagation algorithm led to the best minimisation of the error computed over all the patterns. Relative errors on the thermodynamic and kinetic parameters were evaluated and compared to those obtained with the usual thermal analysis methods. The results obtained are very promising, and the errors are much lower than with usual methods, especially in the presence of noisy signals. This study shows that simulated thermoanalytical curves produced by Joule effect may be used for the deconvolution of the response of the apparatus, by using artificial neural networks.

Journal of High Energy Physics

Sophisticated machine learning techniques have promising potential in search for physics beyond Standard Model in Large Hadron Collider (LHC). Convolutional neural networks (CNN) can provide powerful tools for differentiating between patterns of calorimeter energy deposits by prompt particles of Standard Model and long-lived particles predicted in various models beyond the Standard Model. We demonstrate the usefulness of CNN by using a couple of physics examples from well motivated BSM scenarios predicting long-lived particles giving rise to displaced jets. Our work suggests that modern machine- learning techniques have potential to discriminate between energy deposition patterns of prompt and long-lived particles, and thus, they can be useful tools in such searches.